CN112907361A - Method and device for processing loan application - Google Patents
Method and device for processing loan application Download PDFInfo
- Publication number
- CN112907361A CN112907361A CN202110336788.3A CN202110336788A CN112907361A CN 112907361 A CN112907361 A CN 112907361A CN 202110336788 A CN202110336788 A CN 202110336788A CN 112907361 A CN112907361 A CN 112907361A
- Authority
- CN
- China
- Prior art keywords
- loan application
- application request
- approval
- score
- determining
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 118
- 238000000034 method Methods 0.000 title claims abstract description 71
- 230000004044 response Effects 0.000 claims abstract description 40
- 238000012549 training Methods 0.000 claims description 33
- 238000013528 artificial neural network Methods 0.000 claims description 28
- 238000013145 classification model Methods 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 24
- 238000009825 accumulation Methods 0.000 claims description 17
- 238000012550 audit Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 9
- 238000013138 pruning Methods 0.000 claims description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000007418 data mining Methods 0.000 abstract description 2
- 238000011835 investigation Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000007726 management method Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 239000003795 chemical substances by application Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000035606 childbirth Effects 0.000 description 1
- 239000013256 coordination polymer Substances 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- -1 electricity Substances 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Finance (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a method and a device for processing loan application, relates to the field of big data analysis and mining, and particularly relates to the field of artificial intelligence. One specific implementation mode comprises the steps of receiving a loan application request, calling a real-time approval component, and further acquiring user information corresponding to the loan application request based on a preset information query interface; calling a preset approval rule base, and further performing preliminary approval on the loan application request based on a preset internal control list and user information; in response to the result that the preliminary examination and approval of the loan application request is determined to be passed, calling a pre-trained credit scoring model and determining a score corresponding to the user information; and determining a processing mode and a payment mode corresponding to the loan application request based on the scores, and processing the loan application request according to the processing mode and the payment mode. Therefore, the method and the device for loan approval can solve the problems that the existing loan approval is poor in timeliness and high in approval cost.
Description
Technical Field
The application relates to the field of big data analysis and mining, in particular to the field of artificial intelligence, and particularly relates to a method and a device for processing loan application.
Background
At present, the loan service of farmers is large in number of strokes, small in single stroke amount and rich in data. The farmer loan approval mainly adopts a mode of combining offline application and offline approval or online application and offline approval.
In the process of implementing the present application, the inventor finds that at least the following problems exist in the prior art:
the examination and approval under the peasant household loan line is too dependent on the subjective judgment of the peasant household manager, the requirements on the experience and personal quality of the peasant household manager are too high, the examination and approval timeliness is poor, and the examination and approval cost is high.
Disclosure of Invention
In view of this, embodiments of the present application provide a method and an apparatus for processing a loan application, which can solve the problems of poor approval timeliness and high approval cost of the existing loan.
To achieve the above object, according to an aspect of an embodiment of the present application, there is provided a method for processing a loan application, including:
receiving a loan application request, invoking a real-time approval component,
further acquiring user information corresponding to the loan application request based on a preset information query interface;
calling a preset approval rule base, and further performing preliminary approval on the loan application request based on a preset internal control list and user information;
in response to the result that the preliminary examination and approval of the loan application request is determined to be passed, calling a pre-trained credit scoring model and determining a score corresponding to the user information;
and determining a processing mode and a payment mode corresponding to the loan application request based on the scores, and processing the loan application request according to the processing mode and the payment mode.
Optionally, determining a processing method and a payment method corresponding to the loan application request based on the score includes:
determining a processing mode of the loan application request according to the score and a preset score interval;
and determining a payment mode corresponding to the loan application request according to the score, the preset score interval and the processing mode.
Optionally, before determining the processing manner and the payment manner corresponding to the loan application request based on the score, the method further includes:
determining a pre-granted credit limit based on the user information; and
according to the scores and the preset score interval, the processing mode for determining the loan application request comprises the following steps:
triggering an opening and paying process in response to the fact that the score is located in the first score interval, and further performing opening and paying based on the pre-granted credit line and the loan application request;
in response to the fact that the scores are located in the second score interval, selecting an auditor node corresponding to the second score interval in the audit role pool, and sending the loan application request to the corresponding auditor node for audit;
and triggering an ending process in response to determining that the score is located in the third grading interval, and further sending an indication of refusing the loan application request.
Optionally, the user information includes asset information, inventory room credit, commission wage and accumulation fund payment information; and
determining a pre-granted credit limit based on the user information, comprising:
determining a first credit line corresponding to the asset information, a second credit line corresponding to the inventory house credit, a third credit line corresponding to the surreptitious wages and a fourth credit line corresponding to the public accumulation fund payment information;
determining a pre-granted credit line according to the first credit line, the second credit line, the third credit line, the fourth credit line and the adjusting coefficient; wherein the adjustment factor is derived based on the number of credit lines used in determining the pre-granted credit line.
Optionally, the preset approval rule base includes at least one rejection rule; and
calling a preset examination and approval rule base, and then carrying out preliminary examination and approval on the loan application request based on a preset internal control list and user information, wherein the method comprises the following steps:
in response to the fact that the user corresponding to the loan application request is not in a preset internal control list, judging whether the user information meets at least one loan rejection rule;
in response to determining that the user information does not satisfy the at least one repudiation rule, determining that the result of the preliminary approval is a pass.
Optionally, the method for processing a loan application further comprises:
acquiring an initial neural network;
acquiring a training sample set, wherein the training sample set comprises historical user information of each user corresponding to a historical loan application request and a corresponding historical primary examination and approval result;
taking historical user information in the training sample set as input of an initial neural network, taking a historical preliminary approval result corresponding to the input historical user information as expected output, and training the initial neural network to obtain a pre-trained classification model;
performing network structure pruning on the pre-trained classification model to obtain a simplified classification model;
and extracting at least one rejection rule from the simplified classification model to form a preset examination and approval rule base.
In addition, the present application provides an apparatus for processing a loan application, comprising:
a receiving unit configured to receive a loan application request, invoke a real-time approval component;
the loan application system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is configured to acquire user information corresponding to a loan application request based on a preset information query interface;
the approval unit is configured to call a preset approval rule base, and further perform preliminary approval on the loan application request based on a preset internal control list and user information;
a score determining unit configured to, in response to determining that the result of the preliminary approval of the loan application request is passed, invoke a pre-trained credit scoring model to determine a score corresponding to the user information;
and the processing unit is configured to determine a processing mode and a payment mode corresponding to the loan application request based on the scores, and process the loan application request according to the processing mode and the payment mode.
Optionally, the processing unit is further configured to:
determining a processing mode of the loan application request according to the score and a preset score interval;
and determining a payment mode corresponding to the loan application request according to the score, the preset score interval and the processing mode.
Optionally, the apparatus for processing a loan application further comprises:
a pre-granted credit line determination unit configured to determine a pre-granted credit line based on the user information; and
the processing unit is further configured to:
triggering an opening and paying process in response to the fact that the score is located in the first score interval, and further performing opening and paying based on the pre-granted credit line and the loan application request;
in response to the fact that the scores are located in the second score interval, in the audit role pool, the auditor node corresponding to the second score interval is selected, and the loan application request is sent to the corresponding auditor node to be audited
And triggering an ending process in response to determining that the score is located in the third grading interval, and further sending an indication of refusing the loan application request.
Optionally, the user information includes asset information, inventory room credit, commission wage and accumulation fund payment information; and
the pre-granted credit line determination unit is further configured to:
determining a first credit line corresponding to the asset information, a second credit line corresponding to the inventory house credit, a third credit line corresponding to the surreptitious wages and a fourth credit line corresponding to the public accumulation fund payment information;
determining a pre-granted credit line according to the first credit line, the second credit line, the third credit line, the fourth credit line and the adjusting coefficient; wherein the adjustment factor is derived based on the number of credit lines used in determining the pre-granted credit line.
Optionally, the preset approval rule base includes at least one rejection rule; and
the approval unit is further configured to:
in response to the fact that the user corresponding to the loan application request is not in a preset internal control list, judging whether the user information meets at least one loan rejection rule;
in response to determining that the user information does not satisfy the at least one repudiation rule, determining that the result of the preliminary approval is a pass.
Optionally, the apparatus further comprises an approval rule base determination unit configured to:
acquiring an initial neural network;
acquiring a training sample set, wherein the training sample set comprises historical user information of each user corresponding to a historical loan application request and a corresponding historical primary examination and approval result;
taking historical user information in the training sample set as input of an initial neural network, taking a historical preliminary approval result corresponding to the input historical user information as expected output, and training the initial neural network to obtain a pre-trained classification model;
performing network structure pruning on the pre-trained classification model to obtain a simplified classification model;
and extracting at least one rejection rule from the simplified classification model to form a preset examination and approval rule base.
In addition, the present application provides an electronic device for processing a loan application, comprising: one or more processors; a storage device for storing one or more programs which, when executed by one or more processors, cause the one or more processors to implement a method for processing a loan application as described above.
Additionally, the present application provides a computer readable medium having stored thereon a computer program which, when executed by a processor, implements a method for processing a loan application as described above.
One embodiment of the above invention has the following advantages or benefits: the method comprises the steps of receiving a loan application request, calling a real-time approval component, and further acquiring user information corresponding to the loan application request based on a preset information query interface; and calling a preset approval rule base, and then carrying out preliminary approval on the loan application request based on a preset internal control list and user information so as to preliminarily screen the loan application request meeting loan application conditions, thereby improving the loan approval speed and accuracy. And when the result of the preliminary examination and approval of the loan application request is determined to be passed, the score corresponding to the user information can be more accurately determined by adopting the neural network technology and calling the pre-trained credit scoring model. The processing mode and the payment mode corresponding to the loan application request are determined based on the obtained scores, so that the loan application request can be processed in a differentiated mode according to the obtained processing mode and the payment mode, the risk is reduced when a high-limit loan is provided for high-quality farmers, and loan funds are effectively prevented from being used.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a further understanding of the application and are not to be construed as limiting the application. Wherein:
fig. 1 is a schematic view of the main flow of a method for processing a loan application according to a first embodiment of the application;
fig. 2 is a schematic view of the main flow of a method for processing a loan application according to a second embodiment of the application;
fig. 3 is a schematic view of an application scenario of the method for processing a loan application according to the third embodiment of the present application;
FIG. 4 is a schematic diagram of the main modules of an apparatus for processing a loan application according to an embodiment of the application;
FIG. 5 is an exemplary system architecture diagram to which embodiments of the present application may be applied;
fig. 6 is a schematic structural diagram of a computer system suitable for implementing the terminal device or the server according to the embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic view of the main flow of a method for processing a loan application according to a first embodiment of the present application, and as shown in fig. 1, the method for processing a loan application includes:
and step S101, receiving a loan application request and calling a real-time approval component.
And step S102, obtaining user information corresponding to the loan application request based on a preset information query interface.
In this embodiment, an executing entity (for example, a server) of the method for processing a loan application may receive a loan application request from a terminal operated by a user through a wired connection or a wireless connection, and call a real-time approval component to obtain user information corresponding to the loan application request based on a preset information query interface. For example, the information query interface of the credit institution receiving the loan application request is called, the in-line credit investigation information of the credit institution corresponding to the loan application request is obtained, and the in-line credit investigation interface is called to obtain the in-line credit investigation information corresponding to the loan application request. The inline credit information characterizes identification information, loan information, credit card information, etc. of the credit institution that the user submitting the loan application request is at receiving the loan application request. The human credit investigation information represents identification information, loan information, credit card information, etc. of each credit agency under the name of the user submitting the loan application request. The identity identification information comprises a name, an identity card number and a home address. Work units, etc. The loan information comprises a loan issuing bank, loan amount, loan term, repayment mode, actual repayment record and the like. The credit card information comprises information of public service fees such as card issuing banks, credit granting amount, repayment records, personal payment telephone, water, electricity, gas and the like, and public information such as court civil judgment, tax owed and the like, so as to comprehensively reflect the credit condition of the loan application user.
And step S103, calling a preset approval rule base, and further performing preliminary approval on the loan application request based on a preset internal control list and user information.
After receiving a loan application request initiated by a user (for example, a farmer) and acquiring user information corresponding to the loan application request, an executing entity may first invoke a preset internal control list in a real-time approval component to determine whether the user is in the preset internal control list. And calling a preset approval rule base in the real-time approval component to preliminarily approve the user information corresponding to the obtained loan application request so as to determine whether the user has the qualification of loan.
In this embodiment, the data format of the internal control list may include contents such as a serial number, a certificate type, a certificate number, a name, an import reason, an admission suggestion (branch termination and adjustment subtraction), and a remark. After the executive body receives the loan application request submitted by the user, the executive body can call a preset internal control list in the real-time approval component, and match the contents such as serial numbers, certificate types, certificate numbers, names, import reasons, admission suggestions (branch termination and adjustment), remarks and the like in the user information with the corresponding contents in the preset internal control list so as to determine whether the user is in the preset internal control list. The users with risks are stored in the preset internal control list. And if the internal control list is judged to be terminated based on the preset internal control list, the execution main body prompts error information when receiving the user application and paying the user loan. And if the executive body judges that the credit line is adjusted and reduced, multiplying the credit line calculated by the preset rule by a preset coefficient to obtain the credit line applicable to the user when the executive body receives the user application and pays the user credit. The assignment of the preset coefficient is not specifically limited in the present application.
In this embodiment, the user information may include information such as age, nationality, sex, work condition (working age, current work, etc.), payment application time limit, account deposit balance, and whether marriage and childbirth is required. The preset approval rule base can include the following preset rules: if the user age is more than 65 years old, rejecting the loan; if the user age is less than 20 years old, rejecting the loan; if the user is not China nationality, refusing the loan; if the user is male and does not work, refusing the loan; if the working life of the user is less than 3 years and the user is not married, refusing the loan; if the repayment date of the user is longer than 12 months and the working year is less than 3 years, refusing the loan; if the deposit balance of the user account is less than 1 ten thousand yuan and no work is carried out, refusing the loan; if the user is unbelided and not working by women, the user is withheld. The results of the preliminary approval of the loan application request are a pass loan application request and a fail loan application request.
And step S104, in response to the fact that the result of the preliminary examination and approval of the loan application request is passed, calling a pre-trained credit scoring model, and determining the score corresponding to the user information.
And when the executive body determines that the result of the preliminary examination and approval of the fine application is passed, calling a pre-trained credit scoring model (or scoring card mechanism) in the real-time examination and approval component, inputting the user information into the pre-trained credit scoring model, and outputting a score corresponding to the user information.
And step S105, determining a processing mode and a payment mode corresponding to the loan application request based on the scores, and processing the loan application request according to the processing mode and the payment mode.
After obtaining the score corresponding to the user information, the executive body may determine a processing mode and a payment mode corresponding to the loan application request based on the corresponding relationship between the score and the processing mode and the payment mode, and process the loan application request according to the processing mode and the payment mode.
In this embodiment, the pre-trained credit scoring model may be obtained by training through the following steps: acquiring an initial neural network; acquiring a training sample set, wherein the training sample set comprises historical user information of each user corresponding to a historical loan application request, scores corresponding to the historical user information, and processing modes and payment modes corresponding to the corresponding scores; and taking the historical user information in the training sample set as the input of an initial neural network, taking the score corresponding to the input historical user information and the corresponding processing mode and payment mode as expected outputs, and training the initial neural network to obtain a pre-trained credit scoring model. The executive body can input the user information corresponding to the loan application request into the pre-trained credit scoring model, so that the processing mode and the payment mode corresponding to the loan application request are output while the score corresponding to the user information is output.
The processing mode can include direct sign-up and loan-release, sending the loan application request to the corresponding auditing personnel node for auditing and sending an instruction of refusing the loan application. When the processing means is a subscription payout, the payment means may include an autonomous payment, a trusted payment, and a consumption payment. The self-payment means that the loan fund can be used by the borrowing user without examination and approval, but if the borrowing user violates the borrowing contract to use the loan fund, the credit agency has the right to settle the loan fund in advance at any time. The trusted payment adds an "audit of the loan fund usage" step prior to loan issuance, binding the loan fund and loan usage together. The binding will limit the "free" use of loan funds by the borrower, effectively resolving the problem of appropriating loan funds. The consumption payment does not directly deliver the loan to the user, but rather delivers the loan by the user selecting a loan account to pay when consuming on the network.
In the embodiment, the user information corresponding to the loan application request is acquired based on the preset information query interface by receiving the loan application request and calling the real-time approval component; and calling a preset approval rule base, and then carrying out preliminary approval on the loan application request based on a preset internal control list and user information so as to preliminarily screen the loan application request meeting loan application conditions, thereby improving the loan approval speed and accuracy. And when the result of the preliminary examination and approval of the loan application request is determined to be passed, the score corresponding to the user information can be more accurately determined by adopting the neural network technology and calling the pre-trained credit scoring model. The processing mode and the payment mode corresponding to the loan application request are determined based on the obtained scores, so that the loan application request can be processed in a differentiated mode according to the obtained processing mode and the payment mode, the risk is reduced when a high-limit loan is provided for high-quality farmers, and loan funds are effectively prevented from being used.
Fig. 2 is a schematic main flow chart of a method for processing a loan application according to a second embodiment of the present application, and as shown in fig. 2, the method for processing a loan application includes:
step S201, receiving a loan application request and calling a real-time approval component.
Step S202, based on the preset information query interface, obtaining the user information corresponding to the loan application request.
And step S203, calling a preset approval rule base, and further performing preliminary approval on the loan application request based on a preset internal control list and user information.
The principle of step S201 to step S203 is similar to that of step S101 to step S103, and is not described here again.
In this embodiment, the preset approval rule base includes at least one rejection rule.
Specifically, step S203 can also be realized by step S2031 to step S2032:
step S2031, in response to determining that the user corresponding to the loan application request is not in the preset internal control list, determining whether the user information satisfies at least one loan rejection rule.
Step S2032, in response to determining that the user information does not satisfy the at least one rejection rule, determining that the result of the preliminary approval is passed.
In this embodiment, when the executive body determines that the user corresponding to the loan application request is not in the preset internal control list, the credit investigation information in the user information may be checked, and if the credit investigation frequency, the personal loan overdue record and the like in the credit investigation information do not satisfy any loan rejection rule, the initial approval is passed. If any piece of information in the credit investigation information meets the rejection rule, the preliminary examination and approval is not passed. The loan rejection rules may include, for example, that the credit inquiry times are greater than a preset threshold, the overdue times in the overdue records are greater than a preset threshold, and all the standards in the loan rejection rules are configured as parameters, and may be dynamically adjusted according to the indexes such as the reject rate of the loan.
According to the method and the system, whether the loan application request of the user passes through is preliminarily approved based on the preset internal control list and the credit investigation information in the user information, so that further approval can be performed based on the result of the preliminary approval, and the approval of the loan application of the user can be more accurate.
And step S204, in response to the fact that the result of the preliminary examination and approval of the loan application request is passed, calling a pre-trained credit scoring model, and determining the score corresponding to the user information.
The principle of step S204 is similar to that of step S104, and is not described here again.
In some optional implementation manners of this embodiment, the step S204 of "calling the pre-trained credit scoring model and determining the score corresponding to the user information" may be specifically implemented in the following manner:
first, when the pre-trained credit scoring model determines the score corresponding to the user information, the required data may include: province information, account interest, whether the local person is present, total family liability, occupation, gender, highest scholastic history, marital status, and age. After acquiring the data information of the nine aspects, the executive body may input the data information into a pre-trained credit scoring model, so that the pre-trained credit scoring model performs variable construction on six data information (province information, account interest, total liabilities of the family, profession, highest scholarship and age) of the data information. The construction mode is as follows: the province information: according to the past business credit condition and the economic development condition of the area to which the user belongs, the economic development condition of each province, the management level and other factors are comprehensively considered, and the provinces are divided into three categories. Exemplary, the first class province: a, b, c, d, e, f; the second type of province: g, h, i, j, k, l; the third type saves: m, n, o, p. Account interest: and 5 classes are divided according to the sum of interest of the current deposit account in the last year when the user applies for the loan. The first type: interest amount [0, 5 ]; the second type: interest amount [5, 20 ]; in the third category: interest amount [20, 50 ]; the fourth type: interest amount [50, 100 ]; the fifth type: interest amount [100, just infinity ]. Total liability of the family: the following classifications are made according to the total amount of liability of the user's family. The first type: none and unknown; the second type: less than 7 ten thousand; in the third category: 7-10 ten thousand; the fourth type: 10-16 ten thousand; the fifth type: more than 16 million. Occupation: it is classified into five categories according to the occupational properties of users. The first type: leaders of national and institutional enterprises, soldiers; the second type: various technicians, office staff; in the third category: business and service personnel, individual operators; the fourth type: agricultural, forestry, animal husbandry, fishery, water conservancy industry production personnel, production and transportation equipment operators and related personnel; the fifth type: and others. The highest school calendar: and dividing the highest academic records into three categories according to the education condition of the user. The first type: the study is more than born; the second type: the subject; in the third category: major, special and secondary; the fourth type: and others. Age: the ages of the users are divided into four categories. The first type: 18-30 years old; the second type: 30-35 years old; in the third category: 35-50 years old; the fourth type: over 50 years old.
Then, the executive body can call a pre-trained credit scoring model to construct a result according to the variables, and carry out variable replacement. The variable replacement is to replace the Evidence Weight value (WOE) corresponding to the different grouping values of each variable according to the variable construction result. WOE value, which represents one effect on the credit score when the argument takes a certain value. In this embodiment, the variables refer to information such as province information, account interest, whether a local person is present, total liabilities of the family, occupation, gender, highest school history, marital status, and age. For example, the variable one: the WOE value corresponding to the first type of province in the province information is as follows: a; the WOE value corresponding to the second class of provinces is: b; the third class of provinces corresponds to a WOE value of C. For example, the variable two: the WOE value corresponding to the first category in the account information is: a; the second class corresponds to a WOE value of: b; the third class corresponds to a WOE value of: c; the fourth class corresponds to a WOE value of: d; the fifth class corresponds to a WOE value of: E. similarly, the determination methods of the WOE values corresponding to the different grouping values of the variables such as the total liability, the occupation, the highest scholarness, the age, the marital status, the gender, the local person and the like of the family are the same as the determination methods of the WOE values corresponding to the different grouping values of the provincial information and the account interest variable, and are not described herein again.
Finally, the executive body can determine the final score according to the WOE value corresponding to each variable corresponding to the user information corresponding to the loan application request and the weight value of each variable, such as k1, k2, k3, k4, k5, k6, k7, k8, and k 9. For example, the WOE values corresponding to the variables corresponding to the user information corresponding to the loan application request may be: provincial information A, account interest C, whether a local person A, total family liability D, occupation C, gender A, highest academic history C, marital status A and age A. Wherein, A can correspond to 1 point, B can correspond to 2 points, C can correspond to 3 points, D can correspond to 4 points, and E can correspond to 5 points. The weight value k1 may be 0.1, k2 may be 0.2, k3 may be 0.3, k4 may be 0.4, k5 may be 0.5, k6 may be 0.6, k7 may be 0.7, k8 may be 0.8, k9 may be 0.9. The score output by the pre-trained credit scoring model is k1 a + k 2C + k3 a + k 4D + k 5C + k6 a + k 7C + k8 a + k9 a 8.5. The value of each letter ABCDE of the WOE is not specifically limited in the present application. Specific values of the weight values k1, k2, k3, k4, k5, k6, k7, k8, and k9 of the variables are not particularly limited in the present application.
Step S205, based on the user information, determining the pre-granted credit limit.
In this embodiment, the user information includes asset information, inventory room credit, commission wage, and accumulation fund payment information. The enforcement agent may determine the pre-granted credit line based on any one of the subscriber information. For example, the pre-credit line is determined by the corresponding relationship between the surrogated wages and the credit line in the user information.
Specifically, step S205 can also be realized by step S2051 to step S2052:
step S2051, a first credit line corresponding to the asset information, a second credit line corresponding to the inventory house credit, a third credit line corresponding to the commission wage, and a fourth credit line corresponding to the public deposit payment information are determined.
The executive body can determine the pre-granted credit limit at any time based on the user information. The time for determining the pre-granted credit limit is not specifically limited. For example, the determination of the pre-granted credit line before or after the preliminary approval of the subscriber information is not particularly limited. The executive body can call the quota pre-granting module in the real-time examination and approval component to pre-grant the quota for the user according to the contribution degree of the user, namely asset information, inventory house credit, generation wage and public accumulation fund payment. Specifically, the step of carrying out quota pre-credit for the user is as follows: taking an Asset independent Management (AUM) value of the current N months of the month and the day as a base number, and comprehensively considering the stability and trend change condition of the AUM value of the user to obtain a first credit line of corresponding Asset information, namely the AUM value credit line A of the user. The AUM includes personal financial assets such as a user's deposit at a financial institution and various investment products purchased through the financial institution. The investment mainly comprises fund, national debt, insurance, investment financing products issued by financial institutions and the like; taking the mortgage value of the stock room credit as a base number, and comprehensively considering the mortgage rate coefficient, the room yield value-added coefficient, the city regulating coefficient, the stock room credit balance and the like to obtain a second credit line corresponding to the stock room credit, namely the user stock room credit line B; according to the annual income of the user in the surrogated payroll data, considering the storage duration and stability of surrogated payrolls to obtain a third credit line corresponding to surrogated payrolls, namely a user surrogated payroll credit line C; and calculating the expected annual income of the user according to the payment amount and the payment coefficient in the public accumulation fund payment data, and comprehensively considering the time length of the public accumulation fund payment and the account balance to obtain a fourth credit line corresponding to the public accumulation fund payment information, namely the user public accumulation fund credit line D.
Step S2052, determining a pre-granted credit line according to the first credit line, the second credit line, the third credit line, the fourth credit line and the adjustment coefficient.
Wherein the adjustment factor is derived based on the number of credit lines used in determining the pre-granted credit line.
The execution main body can determine the pre-granted credit line according to the preset line output rule, the first credit line, the second credit line, the third credit line, the fourth credit line and the adjusting coefficient. For example, the executive agent may comprehensively merge the four types of credits a-D according to a preset credit output rule, and the final credit output may be: the credit line is Max (a, B, C, D) adjustment factor. The adjustment factor is to increase the amount appropriately when there are multiple indices. For example, when there are 4 dimensions of credit (i.e., credit A, B, C, D are all involved in determining the final credit), then the adjustment factor may be 1.3; if there is a credit line of 3 dimensions (i.e., three of lines A, B, C, D participate in determining the final credit line), then the adjustment factor may be 1.2; where there are 2 dimensions of credit (i.e., two of lines A, B, C, D participate in determining the final credit), then the adjustment factor may be 1.1; if there is only a credit in 1 dimension (i.e., one of lines A, B, C, D participates in determining the final credit), then the adjustment factor may be 1.0.
The embodiment comprehensively considers the contribution degree of the user, particularly the farmer, namely asset information, inventory house credit, agency wages, accumulated fund payment information and the like to carry out quota pre-credit, and carries out differentiated credit on the user, so that the risk is reduced when higher quota is provided for the high-quality user.
And S206, determining a processing mode and a payment mode corresponding to the loan application request based on the scores, and processing the loan application request according to the processing mode and the payment mode.
The principle of step S206 is similar to that of step S105, and is not described here again.
Specifically, step S206 can also be realized by steps S2061 to S2062:
and step S2061, determining a processing mode of the loan application request according to the score and the preset score interval.
Specifically, the executing agent may determine the score interval in which the score is located according to the corresponding relationship between the score and a preset score interval, so as to determine the processing mode of the loan application request corresponding to the score according to the corresponding relationship between the score interval and the processing mode of the loan application request. The processing mode can comprise: and directly signing and paying, sending the loan application request to a corresponding auditing personnel node for auditing and sending an instruction of refusing the loan application.
Specifically, step S2061 may be realized by step S20611 to step S20613:
step S20611, in response to the fact that the score is located in the first score interval, an opening and paying process is triggered, and then opening and paying are conducted based on the pre-granted credit limit and the loan application request.
Step S20612, in response to determining that the score is located in the second score interval, selecting an auditor node corresponding to the second score interval in the audit role pool, so as to send the loan application request to the corresponding auditor node for audit.
Step S20613, in response to determining that the score is located in the third score interval, triggering an ending process, and further sending an indication of refusing the loan application request.
After obtaining the score corresponding to the user information corresponding to the loan application request of the user, the executive body may classify the score and determine the score interval in which the score is located. For example, taking a farmer applying for a loan as an example, the score interval corresponding to the farmer in the high score region may be: >657 points (belonging to the first segment of the score); the score interval corresponding to the farmers in the medium score area can be as follows: 619 points < the score is not more than 657 points (belonging to the first score interval); the score interval corresponding to the peasant household in the low score region may be: 593 points < score not more than 619 points (belonging to the first score interval); the score interval corresponding to the peasant household in the manual judgment area can be as follows: 464 points < the score is not more than 593 points (belonging to the second score interval); the value section corresponding to the farmer in the withholding value section may be: the score is less than or equal to 464 points (belonging to the third score interval). And the executive body responds to the fact that the determined score is located in the first score interval, an opening and paying process is triggered, and then opening and paying are carried out based on the pre-granted credit amount and the loan application request. And the executive body responds to the fact that the score is located in the second grading interval, and selects the corresponding auditor node of the second grading interval in the audit role pool, so that the loan application request is sent to the corresponding auditor node for offline audit. And the executive body responds to the fact that the score is located in the third grading interval, the ending process is triggered, further an indication of refusing the loan application request is sent, and the loan application approval process is ended. The score interval is merely an example, and the specific range of the score interval is not limited.
According to the method, the users are automatically classified according to the set calculation standard, the screening condition and the like, the loan application of the users is determined to be passed or refused according to the classification result, or the loan application of the farmers is approved off line, so that the loan application of the users can be approved quickly and accurately in real time.
And S2062, determining a payment mode corresponding to the loan application request according to the scores, the preset score interval and the processing mode.
Specifically, after determining the processing mode corresponding to the score corresponding to the loan application request of the user, the executive body determines the payment mode corresponding to the score accurately by combining the score interval in which the score is located. For example, when the score corresponding to the user's loan application request is located in the score interval >657 points in the first score interval, the payment mode corresponding to the user's loan application request may be autonomous payment or consumption payment. When the score corresponding to the loan application request of the user is located in a score interval with the score of 619 minutes < the score of 657 minutes or less in the first score interval, the payment mode corresponding to the loan application request of the user can be trusted payment or consumption payment. When the score corresponding to the loan application request of the user is in the score interval of 593 points < the score is less than or equal to 619 points in the first score interval, the payment mode corresponding to the loan application request of the user can be consumption payment. When the score corresponding to the loan application request of the user is located in the second score interval, namely the score interval of 464 scores < the score is less than or equal to 593 scores, the payment mode corresponding to the loan application request of the user can be consumption payment. When the score corresponding to the loan application request of the user is located in the third score interval, that is, the score interval with the score less than or equal to 464 points, the loan application request of the user does not correspond to any payment mode, that is, the payment mode is as follows: none.
The embodiment can effectively solve the problem that loan funds are stolen by determining the payment mode of the loan according to the classification result of the scores corresponding to the loan application request of the user.
In some alternative implementations of the present embodiment, the method for processing a loan application further includes the following steps not shown in fig. 2: acquiring an initial neural network; acquiring a training sample set, wherein the training sample set comprises historical user information of each user corresponding to a historical loan application request and a corresponding historical primary examination and approval result; the execution main body can encode the historical user information and the corresponding historical preliminary approval result, and illustratively, the codes corresponding to the working conditions in the historical user information are respectively 0 unemployed and 1 unemployed; the codes corresponding to the sexes are respectively 0 female and 1 male; the codes corresponding to the marital conditions are respectively unmarried 0 and marred 1; the codes corresponding to the user ages are 0<20 years old, 1>65 years old, 2> -20 & < (65 years old), respectively; the codes corresponding to the working life of the user are respectively 0<3, 1>10, 2 & ═ 10; the codes corresponding to the deposit balance of the user account are respectively 0<10000 and 1> 10000; the codes corresponding to the repayment period are respectively 0<12 and 1> 10000; and the corresponding codes of the user loan approval conclusion are respectively 0 refusal and 1 passing.
Taking a code corresponding to each historical user information in a training sample set as an input of an initial neural network, taking a code corresponding to a historical preliminary approval result corresponding to the input historical user information as an expected output, training the initial neural network to adjust the structure of the initial neural network, and stopping training when the initial neural network can correctly output the codes of the corresponding preliminary approval results for all the codes of the input historical user information, namely achieving an expected training effect, or stopping training when the training times reach a preset threshold value, so as to obtain a pre-trained classification model; performing network structure pruning on the pre-trained classification model by using a pruning algorithm (for example, an Alphabeta pruning algorithm, which is a search algorithm aiming at reducing the number of nodes evaluated by a maximum and minimum algorithm in a search tree of the pre-trained classification model, and the basic idea is to determine whether the current search needs to be continued according to the current optimal result obtained by the previous layer), so as to remove unimportant connections or nodes and simplify the structure of a neural network, thereby obtaining a simplified classification model; finally, adopting a backtracking algorithm: subset ii (subset ii) algorithm (e.g., given a rule base that may contain duplicate rules, all possible subsets of rules in the rule base are returned, and no duplicate subset of rules is contained in the returned subset of rules) extracts at least one withholding rule from the simplified classification model to form a pre-set approval rule base. Therefore, the method simplifies the examination and approval rule base, reduces the complexity of the rules, and can improve the reasoning accuracy of the examination and approval rule base. The new approval rule base can be used for timely adjusting according to the recent loan approval and repayment data of the user, and the loan approval accuracy of the user (such as a farmer) is effectively improved.
The present embodiment approves the user's loan application by utilizing the user's loan approval rule base. Aiming at the problems that the examination and approval rule base is incomplete or inconsistent in knowledge and the like, the neural network technology is adopted, the knowledge refinement is carried out on the examination and approval rule base by utilizing the historical user information of the user loan examination and approval and the corresponding historical preliminary examination and approval results, and the accuracy of the preliminary examination and approval based on the examination and approval rule base can be effectively improved.
Fig. 3 is a schematic view of an application scenario of the method for processing a loan application according to the third embodiment of the present application. The method for processing the loan application is applied to the scenes of the loan application of farmers in the field of mobile interconnection. The farmer loan is a loan issued by a credit institution by taking a personal farmer as a target, and mainly comprises a farmer consumption loan and a farmer production and management loan. The farmer loan application has more application strokes and small single application amount.
In this embodiment, after receiving a loan application initiated by a farmer, a background server of the credit agency may call the real-time approval component to obtain user information corresponding to the loan application request based on a preset information query interface. The real-time approval component can comprise an internal control list checking module, a credit investigation information checking module, an approval rule base module, a limit pre-credit module and a grading card module. The user information may include inline credit information and personal credit information.
The background server can call the monitoring and early warning module in the background server to update the internal control list in real time so as to be called by the internal control list checking module. The background server can call a preset approval rule base in the approval rule base module, and then performs preliminary approval on the loan application request based on the checking result of the internal control list checking module on the real-time updated preset internal control list and the checking result of the credit investigation information checking module on the acquired user information. And checking credit information of the users who are not rejected by the preset internal control list. If the credit investigation times, the personal loan overdue records, the overdue records of the credit card and the quasi credit card meet any one of the loan rejection rules (the loan rejection rules, for example, may include that the credit investigation times are greater than a preset threshold, the overdue times in the overdue records are greater than a preset threshold, and the like), all the standards in the loan rejection rules are configured as parameters, and dynamic adjustment may be performed according to indexes such as the fraction defective of the loan), the check result is a loan rejection. Credit cards are divided into credit cards and quasi-credit cards, and the credit cards refer to credit cards which have a certain credit line and can be consumed first and then paid within the credit line; the quasi-credit card refers to a quasi-credit card which is paid with a certain amount of reserve money by a card holder according to the requirement and can overdraft in a specified credit line when the balance of a reserve money account is insufficient for payment.
The background server responds to the result that the preliminary examination and approval of the loan application request is determined to be passed, and can call the quota pre-granting module to pre-grant the quota based on Asset Management scale (AUM) value, agency wages, inventory room loan and public accumulation fund information in the user information. The AUM value is a measure of the contribution of the farmer to the credit agency. The AUM includes personal financial assets such as deposits made by farmers at financial institutions and various investment products purchased through financial institutions. The investment mainly comprises fund, national debt, insurance, investment financing products issued by financial institutions and the like. The inventory room loan refers to the part of the personal housing loan issued before the new administration station in 2008, 10 and 27 months, which is not yet cleared.
The background server can call a credit scoring model pre-trained in the scoring card module to determine a score corresponding to the user information. And the background server determines a processing mode and a payment mode corresponding to the loan application request based on the scores and processes the loan application request according to the processing mode and the payment mode. For example, the scoring card module may automatically classify users (for example, into approved users, rejected users and manual approval users) according to the set calculation standard and the screening rule by using the user application data, the human bank credit information, the credit card behavior score and the related information in the user information system in the user information corresponding to the loan application request of the user, and output the score and the system suggestion result of each user participating in scoring.
Fig. 4 is a schematic diagram of the main modules of an apparatus for processing a loan application according to an embodiment of the application. As shown in fig. 4, the apparatus for processing a loan application includes a receiving unit 401, an acquiring unit 402, an approving unit 403, a score determining unit 404, and a processing unit 405.
A receiving unit 401 configured to receive a loan application request, invoke a real-time approval component; .
The obtaining unit 402 is configured to obtain user information corresponding to the loan application request based on a preset information query interface.
The approval unit 403 is configured to invoke a preset approval rule base, and further perform a preliminary approval on the loan application request based on a preset internal control list and the user information.
The score determination unit 404 is configured to, in response to determining that the result of the preliminary approval of the loan application request is passed, invoke a pre-trained credit scoring model to determine a score corresponding to the user information.
The processing unit 405 determines a processing method and a payment method corresponding to the loan application request based on the score, and processes the loan application request according to the processing method and the payment method.
In some embodiments, the processing unit 405 is further configured to: determining a processing mode of the loan application request according to the score and a preset score interval; and determining a payment mode corresponding to the loan application request according to the score, the preset score interval and the processing mode.
In some embodiments, the means for processing the loan application further comprises: a pre-granted credit line determination unit configured to determine a pre-granted credit line based on the user information; and the processing unit 405 is further configured to: triggering an opening and paying process in response to the fact that the score is located in the first score interval, and further performing opening and paying based on the pre-granted credit line and the loan application request; in response to the fact that the scores are located in the second score interval, selecting an auditor node corresponding to the second score interval in the audit role pool, and sending the loan application request to the corresponding auditor node for audit; and triggering an ending process in response to determining that the score is located in the third grading interval, and further sending an indication of refusing the loan application request.
In some embodiments, the user information includes asset information, inventory housing, commission wage, and accumulation fund contribution information; and the pre-granted credit line determination unit is further configured to: determining a first credit line corresponding to the asset information, a second credit line corresponding to the inventory house credit, a third credit line corresponding to the surreptitious wages and a fourth credit line corresponding to the public accumulation fund payment information; determining a pre-granted credit line according to the first credit line, the second credit line, the third credit line, the fourth credit line and the adjusting coefficient; wherein the adjustment factor is derived based on the number of credit lines used in determining the pre-granted credit line.
In some embodiments, the preset approval rule base comprises at least one rejection rule; and the approval unit 403 is further configured to: in response to the fact that the user corresponding to the loan application request is not in a preset internal control list, judging whether the user information meets at least one loan rejection rule; in response to determining that the user information does not satisfy the at least one repudiation rule, determining that the result of the preliminary approval is a pass.
In some embodiments, the means for processing the loan application further comprises: an approval rule base determination unit configured to: acquiring an initial neural network; acquiring a training sample set, wherein the training sample set comprises historical user information of each user corresponding to a historical loan application request and a corresponding historical primary examination and approval result; taking historical user information in the training sample set as input of an initial neural network, taking a historical preliminary approval result corresponding to the input historical user information as expected output, and training the initial neural network to obtain a pre-trained classification model; performing network structure pruning on the pre-trained classification model to obtain a simplified classification model; and extracting at least one rejection rule from the simplified classification model to form a preset examination and approval rule base.
It should be noted that the method for processing a loan application and the apparatus for processing a loan application in the present application have corresponding relations in the implementation contents, and therefore, the repeated contents are not described again.
Fig. 5 illustrates an exemplary system architecture 500 for a method for processing a loan application or an apparatus for processing a loan application to which embodiments of the application may be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 serves to provide a medium for communication links between the terminal devices 501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages or the like. The terminal devices 501, 502, 503 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 501, 502, 503 may be various electronic devices having a loan application processing screen, a credit investigation processing screen, and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 505 may be a server that provides various services, such as a back-office management server (for example only) that processes loan application requests submitted by users using the terminal devices 501, 502, 503. The background management server can receive the loan application request, call the real-time approval component, and further obtain user information corresponding to the loan application request based on a preset information query interface; calling a preset approval rule base, and further performing preliminary approval on the loan application request based on a preset internal control list and user information; in response to the result that the preliminary examination and approval of the loan application request is determined to be passed, calling a pre-trained credit scoring model and determining a score corresponding to the user information; and determining a processing mode and a payment mode corresponding to the loan application request based on the scores, and processing the loan application request according to the processing mode and the payment mode so as to solve the problems of poor timeliness and high approval cost of the conventional loan approval.
It should be noted that the method for processing the loan application provided by the embodiment of the present application is generally executed by the server 505, and accordingly, the device for processing the loan application is generally disposed in the server 505.
It should be understood that the number of terminal devices, networks, and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 6, shown is a block diagram of a computer system 600 suitable for use in implementing a terminal device of an embodiment of the present application. The terminal device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of the computer system 600 are also stored. The CPU601, ROM602, and RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output section 607 including a signal processing section such as a Cathode Ray Tube (CRT), a liquid crystal credit authorization inquiry processor (LCD), and the like, and a speaker and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to embodiments disclosed herein, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments disclosed herein include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the system of the present application when executed by the central processing unit (CP U) 601.
It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a receiving unit, an obtaining unit, an approving unit, a score determining unit, and a processing unit. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.
As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium bears one or more programs, and when the one or more programs are executed by the equipment, the equipment receives a loan application request, calls a real-time approval component, and further obtains user information corresponding to the loan application request based on a preset information query interface; calling a preset approval rule base, and further performing preliminary approval on the loan application request based on a preset internal control list and user information; in response to the result that the preliminary examination and approval of the loan application request is determined to be passed, calling a pre-trained credit scoring model and determining a score corresponding to the user information; and determining a processing mode and a payment mode corresponding to the loan application request based on the scores, and processing the loan application request according to the processing mode and the payment mode.
According to the technical scheme of the embodiment of the application, the loan application request is received, the real-time approval component is called, and then the user information corresponding to the loan application request is obtained based on the preset information query interface; and calling a preset approval rule base, and then carrying out preliminary approval on the loan application request based on a preset internal control list and user information so as to preliminarily screen the loan application request meeting loan application conditions, thereby improving the loan approval speed and accuracy. And when the result of the preliminary examination and approval of the loan application request is determined to be passed, the score corresponding to the user information can be more accurately determined by adopting the neural network technology and calling the pre-trained credit scoring model. The processing mode and the payment mode corresponding to the loan application request are determined based on the obtained scores, so that the loan application request can be processed in a differentiated mode according to the obtained processing mode and the payment mode, the risk is reduced when a high-limit loan is provided for high-quality farmers, and loan funds are effectively prevented from being used.
The above-described embodiments should not be construed as limiting the scope of the present application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (14)
1. A method for processing a loan application, comprising:
receiving a loan application request, invoking a real-time approval component,
further acquiring user information corresponding to the loan application request based on a preset information query interface;
calling a preset approval rule base, and further performing preliminary approval on the loan application request based on a preset internal control list and the user information;
in response to the result that the preliminary examination and approval of the loan application request is determined to be passed, calling a pre-trained credit scoring model, and determining a score corresponding to the user information;
and determining a processing mode and a payment mode corresponding to the loan application request based on the scores, and processing the loan application request according to the processing mode and the payment mode.
2. The method of claim 1, wherein determining a processing mode and a payment mode corresponding to the loan application request based on the score comprises:
determining a processing mode of the loan application request according to the score and a preset score interval;
and determining a payment mode corresponding to the loan application request according to the score, a preset score interval and the processing mode.
3. The method of claim 2,
before determining a processing mode and a payment mode corresponding to the loan application request based on the score, the method further comprises:
determining a pre-granted credit limit based on the user information; and
the determining the processing mode of the loan application request according to the score and the preset score interval comprises the following steps:
triggering an opening and paying process in response to the fact that the score is located in a first score interval, and further performing opening and paying based on the pre-granted credit amount and the loan application request;
in response to the fact that the score is located in a second grading interval, selecting an auditor node corresponding to the second grading interval in an audit role pool, and sending the loan application request to the corresponding auditor node for audit;
and triggering an ending process in response to determining that the score is located in the third grading interval, and further sending an indication of refusing the loan application request.
4. The method of claim 3, wherein the user information includes asset information, inventory house credit, commission wage and accumulation fund payment information; and
the determining of the pre-granted credit limit based on the user information comprises the following steps:
determining a first credit line corresponding to the asset information, a second credit line corresponding to the inventory room credit, a third credit line corresponding to the commission wage and a fourth credit line corresponding to the accumulation fund payment information;
determining a pre-granted credit line according to the first credit line, the second credit line, the third credit line, the fourth credit line and an adjusting coefficient; wherein the adjustment coefficient is obtained based on the number of the credit lines used when determining the pre-granted credit line.
5. The method of claim 1, wherein the predetermined approval rule base includes at least one rejection rule; and
the method comprises the following steps of calling a preset examination and approval rule base, and then carrying out preliminary examination and approval on a loan application request based on a preset internal control list and the user information, wherein the examination and approval rule base comprises the following steps:
in response to determining that the user corresponding to the loan application request is not in the preset internal control list, judging whether the user information meets the at least one loan rejection rule;
in response to determining that the user information does not satisfy the at least one lending rejection rule, determining that a result of the preliminary approval is a pass.
6. The method of claim 5, further comprising:
acquiring an initial neural network;
acquiring a training sample set, wherein the training sample set comprises historical user information of each user corresponding to a historical loan application request and a corresponding historical preliminary examination and approval result;
taking the historical user information in the training sample set as the input of the initial neural network, taking a historical preliminary approval result corresponding to the input historical user information as an expected output, and training the initial neural network to obtain a pre-trained classification model;
performing network structure pruning on the pre-trained classification model to obtain a simplified classification model;
and extracting at least one rejection rule from the simplified classification model to form the preset examination and approval rule base.
7. An apparatus for processing a loan application, comprising:
a receiving unit configured to receive a loan application request, invoke a real-time approval component;
the obtaining unit is configured to obtain user information corresponding to the loan application request based on a preset information query interface;
the approval unit is configured to call a preset approval rule base, and further perform preliminary approval on the loan application request based on a preset internal control list and the user information;
a score determining unit configured to, in response to determining that the result of the preliminary approval of the loan application request is passed, invoke a pre-trained credit scoring model to determine a score corresponding to the user information;
and the processing unit is configured to determine a processing mode and a payment mode corresponding to the loan application request based on the scores, and process the loan application request according to the processing mode and the payment mode.
8. The apparatus of claim 7, wherein the processing unit is further configured to:
determining a processing mode of the loan application request according to the score and a preset score interval;
and determining a payment mode corresponding to the loan application request according to the score, a preset score interval and the processing mode.
9. The apparatus of claim 8, further comprising:
a pre-granted credit line determination unit configured to determine a pre-granted credit line based on the user information; and
the processing unit is further configured to:
triggering an opening and paying process in response to the fact that the score is located in a first score interval, and further performing opening and paying based on the pre-granted credit amount and the loan application request;
in response to the fact that the score is located in a second grading interval, selecting an auditor node corresponding to the second grading interval in an audit role pool, and sending the loan application request to the corresponding auditor node for audit;
and triggering an ending process in response to determining that the score is located in the third grading interval, and further sending an indication of refusing the loan application request.
10. The apparatus of claim 9, wherein the user information includes asset information, inventory house credit, commission wage and accumulation fund payment information; and
the pre-granted credit line determination unit is further configured to:
determining a first credit line corresponding to the asset information, a second credit line corresponding to the inventory room credit, a third credit line corresponding to the commission wage and a fourth credit line corresponding to the accumulation fund payment information;
determining a pre-granted credit line according to the first credit line, the second credit line, the third credit line, the fourth credit line and an adjusting coefficient; wherein the adjustment coefficient is obtained based on the number of the credit lines used when determining the pre-granted credit line.
11. The apparatus of claim 7, wherein the predetermined approval rule base comprises at least one rejection rule; and
the approval unit is further configured to:
in response to determining that the user corresponding to the loan application request is not in the preset internal control list, judging whether the user information meets the at least one loan rejection rule;
in response to determining that the user information does not satisfy the at least one lending rejection rule, determining that a result of the preliminary approval is a pass.
12. The apparatus of claim 11, further comprising an approval rule base determination unit configured to:
acquiring an initial neural network;
acquiring a training sample set, wherein the training sample set comprises historical user information of each user corresponding to a historical loan application request and a corresponding historical preliminary examination and approval result;
taking the historical user information in the training sample set as the input of the initial neural network, taking a historical preliminary approval result corresponding to the input historical user information as an expected output, and training the initial neural network to obtain a pre-trained classification model;
performing network structure pruning on the pre-trained classification model to obtain a simplified classification model;
and extracting at least one rejection rule from the simplified classification model to form the preset examination and approval rule base.
13. An electronic device for processing a loan application, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.
14. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110336788.3A CN112907361A (en) | 2021-03-29 | 2021-03-29 | Method and device for processing loan application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110336788.3A CN112907361A (en) | 2021-03-29 | 2021-03-29 | Method and device for processing loan application |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112907361A true CN112907361A (en) | 2021-06-04 |
Family
ID=76109467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110336788.3A Pending CN112907361A (en) | 2021-03-29 | 2021-03-29 | Method and device for processing loan application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112907361A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113744050A (en) * | 2021-09-17 | 2021-12-03 | 中国银行股份有限公司 | Network loan approval method, device and system |
| CN114971879A (en) * | 2022-06-17 | 2022-08-30 | 北京极致车网科技有限公司 | Information processing system and information processing method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7904381B1 (en) * | 2007-02-01 | 2011-03-08 | Federal Home Loan Mortgage Corporation (Freddie Mac) | Systems, methods, and computer products for optimizing the selection of collateral |
| CN106651570A (en) * | 2016-12-27 | 2017-05-10 | 中国建设银行股份有限公司 | System and method for real-time loan approval |
| CN111340616A (en) * | 2020-03-10 | 2020-06-26 | 中国建设银行股份有限公司 | Method, device, equipment and medium for approving online loan |
| CN112184417A (en) * | 2020-09-25 | 2021-01-05 | 中国建设银行股份有限公司 | Business approval method, device, medium and electronic equipment |
-
2021
- 2021-03-29 CN CN202110336788.3A patent/CN112907361A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7904381B1 (en) * | 2007-02-01 | 2011-03-08 | Federal Home Loan Mortgage Corporation (Freddie Mac) | Systems, methods, and computer products for optimizing the selection of collateral |
| CN106651570A (en) * | 2016-12-27 | 2017-05-10 | 中国建设银行股份有限公司 | System and method for real-time loan approval |
| CN111340616A (en) * | 2020-03-10 | 2020-06-26 | 中国建设银行股份有限公司 | Method, device, equipment and medium for approving online loan |
| CN112184417A (en) * | 2020-09-25 | 2021-01-05 | 中国建设银行股份有限公司 | Business approval method, device, medium and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113744050A (en) * | 2021-09-17 | 2021-12-03 | 中国银行股份有限公司 | Network loan approval method, device and system |
| CN114971879A (en) * | 2022-06-17 | 2022-08-30 | 北京极致车网科技有限公司 | Information processing system and information processing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dorfleitner et al. | The fintech market in Germany | |
| Boreiko et al. | New blockchain intermediaries: do ICO rating websites do their job well? | |
| CN110458693A (en) | A kind of automatic measures and procedures for the examination and approval of business loan, device, storage medium and electronic equipment | |
| US9251539B2 (en) | System and method for resolving transactions employing goal seeking attributes | |
| US20130317974A1 (en) | System and method for compiling information for resolving transactions | |
| Mikhaylov et al. | A new stage in the evolution of cryptocurrency markets: Analysis by hurst method | |
| JP2017049673A (en) | Information processing apparatus and information processing method | |
| CN111383091A (en) | Asset securitization pricing method and device | |
| CN110796539A (en) | Credit investigation evaluation method and device | |
| CN111833179A (en) | Resource allocation platform, resource allocation method and device | |
| CN112907361A (en) | Method and device for processing loan application | |
| Murodovich et al. | Improving the Loaning Process in Commercial Banks | |
| CN113034263A (en) | Credit approval method, credit approval device, credit approval server and credit approval medium | |
| CN112767120A (en) | Enterprise evaluation data processing method and device | |
| CN112232950A (en) | Loan risk assessment method and device, equipment and computer-readable storage medium | |
| JP2018067184A (en) | Service provision system for providing service in cooperation with financial asset management system | |
| CN111833180A (en) | Resource allocation method and device | |
| US11238532B2 (en) | Intelligent loan qualification based on future servicing capability | |
| Turdieva et al. | THE IMPACT OF CREDIT RISKS ON AN EFFECTIVE ORGANIZATION IN THE FINANCIAL SERVICES OF COMMERCIAL BANKS | |
| US20210406998A1 (en) | Intelligent loan qualification based on future servicing capability | |
| CN115482083A (en) | Credit granting processing method and device | |
| CN114240605A (en) | Loan calculation method and device, computer equipment and storage medium | |
| CN114240599A (en) | Loan calculation method and device, computer equipment and storage medium | |
| CN114155080A (en) | Fraud identification method, equipment and storage medium | |
| CN112907362A (en) | Loan transaction processing method and device, electronic equipment and storage medium |
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 |